👋 Welcome to Cdani’s blog

1. Introduction 1.1. Intro to the intro I’m not quite sure what this article is—a mix of coding experiment, science communication, and maybe just a fun project for someone who in another life would have wanted to be a physicist. I’ve had this in my drawer for a while, since I read this article by some CERN researchers that explains how you can simulate an experiment on Bell’s inequalities using the Qibo framework....

1. Introduction The quantity of frameworks emerging for GenAI application development is incredible and, in my opinion, is becoming excessive. Every time a new framework appears, it seems to do more or less the same things as the previous one. Perhaps some have better modularization capabilities or more robust design against long-term obsolescence, but they all seem pretty much the same to me and, although I enjoy experimenting, the study of new miraculous and promising GenAI frameworks is becoming less and less appealing....

Introduction During these scorching August days, I took the opportunity to thoroughly read Google’s A2A protocol specification and try to understand how to use its concepts to design an enterprise Agent architecture, possibly free from technological or platform constraints. What is A2A? The Agent2Agent (A2A) Protocol is an open standard designed and publicly shared by Google to facilitate communication and collaboration among AI agents. The standardization of AI interoperability model is a topic that has been discussed since the very first moments when we started talking about Agents, and there are several reasons for this:...

Abstract As AI developers, we’re always looking for ways to make data more accessible and queryable through natural language. While Retrieval-Augmented Generation (RAG) has revolutionized how we interact with unstructired textual documents, it falls short when dealing with structured data. The RAG approach is so powerful that users or even early stage AI developers may fall in the illusion that it can be applied to any kind of data, including structured data like Excel files....

Policy Puppetry Prompt Injection A few days ago, I experimented with some Jailbreaking techniques, which I share in the repo. I started from a HiddenLayer article published a few weeks ago, where the research team described a rather creative and ingenious jailbreaking technique to bypass safety guardrails and the alignment of frontier models. The technique appears to be universal and applicable with a single prompt to multiple models, capable of revealing typically unsafe content or even portions of the native system prompt....